RESUMEN

Background: Retrospective studies evaluating artificial intelligence (AI) algorithms for intracranial hemorrhage (ICH) detection on noncontrast CT (NCCT) have shown promising results but lack prospective validation. Objective: To evaluate the impact on radiologists' real-world aggregate performance for ICH detection and report turnaround times for ICH-positive examinations of a radiology department's implementation of an AI triage and notification system for ICH detection on head NCCT examinations. Methods: This prospective single-center study included adult patients who underwent head NCCT examinations from May 12, 2021 to June 30, 2021 (phase 1) or September 30, 2021 to December 4, 2021 (phase 2). Before phase 1, the radiology department implemented a commercial AI triage system for ICH detection that processed head NCCT examinations and notified radiologists of positive results through a widget with a floating pop-up display. Examinations were interpreted by neuroradiologists or emergency radiologists, who evaluated examinations without and with AI assistance in phase 1 and phase 2, respectively. A panel of radiologists conducted a review process for all examinations with discordance between the radiology report and AI and a subset of remaining examinations, to establish the reference standard. Diagnostic performance and report turnaround times were compared using Pearson chi-square test and Wilcoxon rank-sum test, respectively. Bonferroni correction was used to account for five diagnostic performance metrics (adjusted significance threshold, .01 [α=.05/5]). Results: A total of 9954 examinations from 7371 patients (mean age, 54.8±19.8 years; 3773 female, 3598 male) were included. In phases 1 and 2, 19.8% (735/3716) and 21.9% (1368/6238) of examinations, respectively, were positive for ICH (P=.01). Radiologists without versus with AI showed no significant difference in accuracy (99.5% vs 99.2%), sensitivity (98.6% vs 98.9%), PPV (99.0% vs 99.7%), or NPV (99.7% vs 99.7%) (all P>.01); specificity was higher for radiologists without than with AI (99.8% vs 99.3%, respectively, P=.004). Mean report turnaround time for ICH-positive examinations was 147.1 minutes without AI versus 149.9 minutes with AI (P=.11). Conclusion: An AI triage system for ICH detection did not improve radiologists' diagnostic performance or report turnaround times. Clinical Impact: This large prospective real-world study does not support use of AI assistance for ICH detection.

RESUMEN

Background: Artificial intelligence (AI) algorithms improved detection of incidental pulmonary embolism (IPE) on contrast-enhanced CT (CECT) examinations in retrospective studies; however, prospective validation studies are lacking. Objective: To assess the effect on radiologists' real-world diagnostic performance and report turnaround times of a radiology department's clinical implementation of an AI triage system for detecting IPE on CECT examinations of the chest or abdomen. Methods: This prospective single-center study included consecutive adult patients who underwent CECT of the chest or abdomen for reasons other than PE detection from May 12, 2021 to June 30, 2021 (phase 1) or from July 1, 2021 to September 29, 2021 (phase 2). Before phase 1, the radiology department installed a commercially available AI triage algorithm for IPE detection that automatically processed CT examinations and notified radiologists of positive results through an interactive floating widget. In phase 1, the widget was inactive, and radiologists interpreted examinations without AI assistance. In phase 2, the widget was activated, and radiologists interpreted examinations with AI assistance. A review process involving a panel of radiologists was implemented to establish the reference standard for the presence of IPE. Diagnostic performance and report turnaround times were compared using Pearson Chi-square test and Wilcoxon rank-sum test, respectively. Results: Phase 1 included 1467 examinations in 1434 patients (mean age, 53.8±18.5 years; 753 male, 681 female); phase 2 included 3182 examinations in 2886 patients (mean age, 55.4±18.2 years; 1520 male, 1366 female). The frequency of IPE was 1.4% (20/1467) in phase 1 and 1.6% (52/3182) in phase 2. Radiologists without AI, in comparison with radiologists with AI, showed significantly lower sensitivity (80.0% vs 96.2%, P=.03), without a significant difference in specificity (99.1% vs 99.9%, P=.58), for detection of IPE. The mean report turnaround time for IPE-positive examinations was not significantly different between radiologists without AI and radiologists with AI (78.3 vs 64.6 min, P=.26). Conclusion: An AI triage system improved radiologists' sensitivity for IPE detection on CECT examinations of the chest or abdomen without significant change in report turnaround times. Clinical Impact: This prospective real-world study supports the use of AI assistance for maximizing IPE detection.

Asunto(s)

RESUMEN

Large language models (LLMs) such as ChatGPT are advanced artificial intelligence models that are designed to process and understand human language. LLMs have the potential to improve radiology reporting and patient engagement by automating generation of the clinical history and impression of a radiology report, creating layperson reports, and providing patients with pertinent questions and answers about findings in radiology reports. However, LLMs are error prone, and human oversight is needed to reduce the risk of patient harm.

Asunto(s)

RESUMEN

The use of technology in medicine has grown exponentially because of the technological advancements allowing the digitization of medical data and optimization of their processing to extract multiple features of significant clinical relevance. Radiology has benefited substantially from technical developments and innovations, such as artificial intelligence (AI). This article describes the subsets of AI methods relevant to gastrointestinal and hepatic imaging with examples. We also discuss the evolution of AI, the current challenges, and prospects for further development in the field.

Asunto(s)

RESUMEN

BACKGROUND. In single-institution multireader studies, the liver surface nodularity (LSN) score accurately detects advanced liver fibrosis and cirrhosis and predicts liver decompensation in patients with chronic liver disease (CLD) from hepatitis C virus (HCV). OBJECTIVE. The purpose of this study was to assess the diagnostic performance of the LSN score alone and in combination with the (FIB-4; fibrosis index based on four factors) to detect advanced fibrosis and cirrhosis and to predict future liver-related events in a multiinstitutional cohort of patients with CLD from HCV. METHODS. This retrospective study included 40 consecutive patients, from each of five academic medical centers, with CLD from HCV who underwent nontargeted liver biopsy within 6 months before or after abdominal CT. Clinical data were recorded in a secure web-based database. A single central reader measured LSN scores using software. Diagnostic performance for detecting liver fibrosis stage was determined. Multivariable models were constructed to predict baseline liver decompensation and future liver-related events. RESULTS. After exclusions, the study included 191 patients (67 women, 124 men; mean age, 54 years) with fibrosis stages of F0-F1 (n = 37), F2 (n = 44), F3 (n = 46), and F4 (n = 64). Mean LSN score increased with higher stages (F0-F1, 2.26 ± 0.44; F2, 2.35 ± 0.37; F3, 2.42 ± 0.38; F4, 3.19 ± 0.89; p < .001). The AUC of LSN score alone was 0.87 for detecting advanced fibrosis (≥ F3) and 0.89 for detecting cirrhosis (F4), increasing to 0.92 and 0.94, respectively, when combined with FIB-4 scores (both p = .005). Combined scores at optimal cutoff points yielded sensitivity of 75% and specificity of 82% for advanced fibrosis, and sensitivity of 84% and specificity of 85% for cirrhosis. In multivariable models, LSN score was the strongest predictor of baseline liver decompensation (odds ratio, 14.28 per 1-unit increase; p < .001) and future liver-related events (hazard ratio, 2.87 per 1-unit increase; p = .03). CONCLUSION. In a multiinstitutional cohort of patients with CLD from HCV, LSN score alone and in combination with FIB-4 score exhibited strong diagnostic performance in detecting advanced fibrosis and cirrhosis. LSN score also predicted future liver-related events. CLINICAL IMPACT. The LSN score warrants a role in clinical practice as a quantitative marker for detecting advanced liver fibrosis, compensated cirrhosis, and decompensated cirrhosis and for predicting future liver-related events in patients with CLD from HCV.

Asunto(s)

RESUMEN

This article reviews the essential role of imaging in clinical staging and restaging of renal cell carcinoma (RCC). To completely characterize and stage an indeterminate renal mass, renal CT or MRI without and with IV contrast administration is recommended. The critical items for initial clinical staging of an indeterminate renal mass or of a known RCC according to the TNM staging system are tumor size, renal sinus fat invasion, urinary collecting system invasion, perinephric fat invasion, venous invasion, adrenal gland invasion, invasion of the perirenal (Gerota) fascia, invasion into other adjacent organs, the presence of enlarged or pathologic regional (retroperitoneal) lymph nodes, and the presence of distant metastatic disease. Larger tumor size is associated with higher stage disease and invasiveness, lymph node spread, and distant metastatic disease. Imaging practice guidelines for clinical staging of RCC, as well as the role of renal mass biopsy, are highlighted. Specific findings associated with response of advanced cancer to antiangiogenic therapy and immunotherapy are discussed, as well as limitations of changes in tumor size after targeted therapy. The accurate clinical staging and restaging of RCC using renal CT or MRI provides important prognostic information and helps guide the optimal management of patients with RCC.

Asunto(s)

RESUMEN

BACKGROUND. Incidental homogeneous renal masses are frequently encountered at portal venous phase CT. The American College of Radiology Incidental Findings Committee's white paper on renal masses recommends additional imaging for incidental homogeneous renal masses greater than 20 HU, but single-center data and the Bosniak classification version 2019 suggest the optimal attenuation threshold for detecting solid masses should be higher. OBJECTIVE. The purpose of this article is to determine the clinical importance of small (10-40 mm) incidentally detected homogeneous renal masses measuring 21-39 HU at portal venous phase CT. METHODS. We performed a 12-institution retrospective cohort study of adult patients who underwent portal venous phase CT for a nonrenal indication. The date of the first CT at each institution ranged from January 1, 2008, to January 1, 2014. Consecutive reports from 12,167 portal venous phase CT examinations were evaluated. Images were reviewed for 4529 CT examinations whose report described a focal renal mass. Eligible masses were 10-40 mm, well-defined, subjectively homogeneous, and 21-39 HU. Of these, masses that were shown to be solid without macroscopic fat; classified as Bosniak IIF, III, or IV; or confirmed to be malignant were considered clinically important. The reference standard was renal mass protocol CT or MRI, ultrasound of definitively benign cysts or solid masses, single-phase contrast-enhanced CT or unenhanced MRI showing no growth or morphologic change for 5 years or more, or clinical follow-up 5 years or greater. A reference standard was available for 346 masses in 300 patients. The 95% CIs were calculated using the binomial exact method. RESULTS. Eligible masses were identified in 4.2% of patients (514/12,167; 95% CI, 3.9-4.6%). Of 346 masses with a reference standard, none were clinically important (0%; 95% CI, 0-0.9%). Mean mass size was 17 mm; 72% (248/346) measured 21-30 HU, and 28% (98/346) measured 31-39 HU. CONCLUSION. Incidental small homogeneous renal masses measuring 21-39 HU at portal venous phase CT are common and highly likely benign. CLINICAL IMPACT. The change in attenuation threshold signifying the need for additional imaging from greater than 20 HU to greater than 30 HU proposed by the Bosniak classification version 2019 is supported.

Asunto(s)

RESUMEN

OBJECTIVE. The purpose of this article is to discuss quantitative methods of CT, MRI, and ultrasound (US) for noninvasive staging of hepatic fibrosis. Hepatic fibrosis is the hallmark of chronic liver disease (CLD), and staging by random liver biopsy is invasive and prone to sampling errors and subjectivity. Several noninvasive quantitative imaging methods are under development or in clinical use. The accuracy, precision, technical aspects, advantages, and disadvantages of each method are discussed. CONCLUSION. The most promising methods are the liver surface nodularity score using CT and measurement of liver stiffness using MR elastography or US elastography.

RESUMEN

OBJECTIVE: The objective of our study was to evaluate the cost-effectiveness of active surveillance (AS) versus nephron-sparing surgery (NSS) in patients with a Bosniak IIF or III renal cyst. MATERIALS AND METHODS: Markov models were developed to estimate life expectancy and lifetime costs for 60-year-old patients with a Bosniak IIF or III renal cyst (the reference cases) managed by AS versus NSS. The models incorporated the malignancy rates, reclassification rates during follow-up, treatment effectiveness, complications and costs, and short- and long-term outcomes. An incremental cost-effectiveness analysis was performed to identify management preference under an assumed $75,000 per quality-adjusted life-year (QALY) societal willingness-to-pay threshold, using data from studies in the literature and the 2015 Medicare Physician Fee Schedule. The effects of key parameters were addressed in a multiway sensitivity analysis. RESULTS: The prevalence of malignancy for Bosniak IIF and III renal cysts was 26% (25/96) and 52% (542/1046). Under base case assumptions for Bosniak IIF cysts, the incremental cost-effectiveness ratio of NSS relative to AS was $731,309 per QALY for women, exceeding the assumed societal willingness-to-pay threshold, and AS outperformed NSS for both life expectancy and cost for men. For Bosniak III cysts, AS yielded greater life expectancy (24.8 and 19.4 more days) and lower lifetime costs (cost difference of $12,128 and $11,901) than NSS for men and women, indicating dominance of AS over NSS. Superiority of AS held true in sensitivity analyses for men 46 years old or older and women 57 years old or older even when all parameters were set to favor NSS. CONCLUSION: AS is more cost-effective than NSS for patients with a Bosniak IIF or III renal cyst.

Asunto(s)